© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47975
    Prev
    Next
    INDEX
    Explanations

    go to page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -1.91
    да
    -1.52
    uß
    -1.27
    ↵↵↵↵↵↵
    -1.26
     Melayu
    -1.23
    When
    -1.22
     when
    -1.21
     derajat
    -1.21
    </h2>
    -1.21
    ↵↵↵↵
    -1.20
    POSITIVE LOGITS
     to
    2.33
    ଃ
    1.54
    鬈
    1.52
     inició
    1.40
    !='
    1.36
     truthful
    1.34
     entretenimiento
    1.33
     esfuerzos
    1.33
     miłość
    1.32
     agrí
    1.30
    Activations Density 0.015%

    No Known Activations